DeepBias: Adaptive Framework for In-Depth Probing of Social Biases in LVLMs

Jul 14, 2026

Researchers have introduced DeepBias, an adaptive framework designed to probe social biases in Large Vision-Language Models (LVLMs) more deeply than traditional static datasets allow. DeepBias uses a dynamic loop involving a ProposerAgent that generates test data and a DiggerAgent that iteratively rewrites these tests based on model responses, enabling the exposure of progressively deeper biases. The team also developed DeepBiasBench, a benchmark constructed using an ensemble of five state-of-the-art LVLMs to identify vulnerabilities shared across different architectures.

Why it matters: This work advances LVLM safety assessment by introducing an adaptive, evolutionary approach that reveals deeper and more nuanced model biases than static datasets can uncover.

Full story at: arXiv Computers and Society ↗